© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115996
    Prev
    Next
    INDEX
    Explanations

    admit weakness or vulnerability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Abr
    -0.13
    adar
    -0.13
     Erot
    -0.12
    abr
    -0.12
     karma
    -0.12
     Karma
    -0.12
    .Lang
    -0.12
     Pars
    -0.12
    trx
    -0.12
    prox
    -0.12
    POSITIVE LOGITS
     weakness
    0.26
     vulnerability
    0.21
     weaknesses
    0.20
     weak
    0.19
     Weak
    0.18
     Vulner
    0.18
     vulnerabilities
    0.18
     vulnerable
    0.17
    Weak
    0.16
    weak
    0.15
    Activations Density 0.042%

    No Known Activations